Data◆Video · 21:26 — 23:02

Simulation provides two unique benefits that real-world data cannot: systematic coverage for reliability (controllable variation of all state-space parameters) and accelerated data generation for efficiency (faster-than-real-time training).

Yunzhu Li details how simulation enables systematic randomization of lighting, friction, geometry, and other physical parameters to ensure robust coverage, and allows training at speeds faster than human teleoperation permits. ✦ AI generated

Yunzhu Li · a16z Podcast · 2026-07-28 · original ↗

Share card ↓Export .md Export .txt

starts at this moment · 21:26

Simulation can provide two levels of benefits. The first one is reliability and the second one is efficiency. For reliability, if you're thinking about a robotic system working reliable in the real environments, you need data to provide systematic coverage of all the state space and the variations that robots might encounter. That's how you can learn of how that is robust. So with simulation, you can do systematic randomizations and control the variations of lighting, frictions, geometries, object types and also all different kind of physical parameters to make sure you have sufficient coverage of the state space. Second is about efficiency. Right now many people are doing teleoperation and you're collecting the data at a speed that is actually slower than human actually doing the task. For many of our clients human speed is not good enough. They want faster than human speeds. In simulation, you can do systematic speed up of the robots behaviors to train the robots such that it considers all the dynamics changes of the environments.

verbatim transcript · starts at 21:26

Transcript · around this moment

21:26>> I also want to add to that. So like there are if you put things more specific simulation can provide two levels of benefits. The first one is reliability and the second one is efficiency. So for reliability, if you're thinking about a robotic system working reliable in the real environments, you need data to provide systematic coverage of all the state space and the variations that robots might encounter. That's how you can

21:52learn of how that is robust. So with simulation, you can do systematic randomizations and control and the variations of lighting, frictions, geometries, object types and also all different kind of physical parameters to making sure you have sufficient coverage of the state space. So this is what can give the robotic systems reliability and second is about efficiency. So right now many people are doing tele operation and if you look at many of the television

22:19device imagining all the actual skeletons you are using you're actually collecting the data at a speed that is actually slower than human actually doing the task. >> But for many of our clients human speed to them is not good enough. They want faster than human speeds. Yeah. >> So for the robot to like move faster, it's not as simple as just drive the robot faster because the gravity doesn't

22:39change. >> But in simulation, you can do systematic speed up of the robots behaviors to train the robots such that it considers all the dynamics changes of the environments. So this is what's can give like our clients for them efficiency. So both for the reliability and efficiency though there are some kind of like a very unique like values where simulation can provide. You've talked about the technology and the platform, what it

23:03does. Maybe talk about the specific use cases people use it for. >> There are essential like two specific use cases especially around both training and also around evaluations. >> Okay. >> Um starting from the evaluations. >> So evaluation is something like people often overlooked in the robotics >> but if you are tuning like robotic models you have to know how well it works and that is the only source of

23:27information for you to iterate. >> Yeah. By the way, a lot of a lot every every AI person really understands what eval are and uses it all the time. NonAI people, it often means something a little different. So maybe it's even worth just describing specifically what you mean by evaluation. >> Okay. So what I mean by evaluation is you'll be able to understand for this specific checkpoints how well does it

▦ Synix

Around this claim

Evidence · 3

The unique bottleneck in general-purpose robotics is the lack of data for training and evaluation, which can be solved by a 'real-to-sim-to-real' pipeline that aligns digital worlds with physical environments so that simulation data replaces real-world data at scale.Yunzhu Li · a16z Podcast · conf 100%Simulation provides two distinct benefits for robotics: reliability through systematic randomization covering the full state space, and efficiency through controllable speed-up of robot behaviors that is impossible in the physical world.Yunzhu Li · a16z Podcast · conf 100%Scene simulation provides reliability and efficiency that real-world data cannot, by enabling systematic randomization and coverage of the state space for robust robot training, and by allowing faster-than-human training speeds.Yunu Guo · a16z Podcast · conf 85%

This moment responds to

extends → The real-to-sim-to-real pipeline maps real environments into aligned digital worlds to replace costly real-world data collection with scalable simulation data for robotics training and evaluation.Yunzhu Li · a16z Podcast extends → Simulation is not an alternative to real-world data but plays a critical complementary role that real data cannot fill: counterfactual reasoning — playing out events that haven't happened, cannot happen, or lack sufficient real-world data.Fei-Fei Li · a16z Podcast extends → The role simulation plays that real-world data cannot is counterfactual reasoning—playing out events that haven't happened or cannot happen—and this is critical for robotics because we cannot possibly have enough real-world data.Fei-Fei Li · a16z Podcast provides context → The next frontier of AI is spatial intelligence — creating AI that can generate, understand, reason with, and interact with physical or virtual spaces.Fei-Fei Li · a16z Podcast